DocumentCode :
3483841
Title :
LDA based color information fusion for visual objects tracking
Author :
Qi, Fei ; Song, Xiaowei ; Shi, Guangming
Author_Institution :
Sch. of Electron. Eng., Xidian Univ., Xi´´an, China
fYear :
2009
fDate :
7-10 Nov. 2009
Firstpage :
2201
Lastpage :
2204
Abstract :
In this paper, an approach for object tracking is proposed based on the online color information fusion scheme. The fusion scheme, is performed by projecting multi-channel color images to a one-dimensional pseudo gray scale space. This dimensionality reduction simplifies the designation of the tracking algorithm. The fusing coefficients are determined by taking the Fisher linear discriminant analysis to maximize the discriminative capability after taking the projection. The robustness of the approach lies in exploiting the appearance discrimination of the object in cluttered scenarios with varying illumination conditions. This scheme is embedded into a mean-shift tracking system and the experimental results show our scheme can enhance the discriminant characters in the changing environment and hence producing robust tracking results.
Keywords :
image colour analysis; target tracking; Fisher linear discriminant analysis; mean-shift tracking system; multichannel color images; one-dimensional pseudo gray scale space; online color information fusion scheme; visual objects tracking; Algorithm design and analysis; Application software; Color; Computer vision; Feature extraction; Layout; Lighting; Linear discriminant analysis; Object detection; Robustness; Fisher Linear Discriminant Analysis; classification; feature extraction; fusion; tracking;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing (ICIP), 2009 16th IEEE International Conference on
Conference_Location :
Cairo
ISSN :
1522-4880
Print_ISBN :
978-1-4244-5653-6
Electronic_ISBN :
1522-4880
Type :
conf
DOI :
10.1109/ICIP.2009.5413870
Filename :
5413870
Link To Document :
بازگشت